monitor
CommunityReal-time safety monitor for agent operations.
Software Engineering#monitoring#safety#alerting#plan-review#agent-operations#destructive-patterns#secrets-exposure
Authorgwpjp
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill provides a real-time safety monitor that watches agent operations to detect and block dangerous actions, such as destructive commands, malicious packages, and leakage of secrets.
Core Features & Use Cases
- Detect destructive commands and risky operations in plan reviews, code changes, and execution steps and prompt immediate intervention.
- Identify suspicious or tampered packages and credential or secret exposure, generating alerts and preventing execution.
- Use cases include safeguarding automated workflows, during plan reviews, code review, and bash command execution by agents.
Quick Start
Invoke the safety monitor to review planned actions or recent activity before agents execute commands.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: monitor Download link: https://github.com/gwpjp/Web3-Claude/archive/main.zip#monitor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.